pith. machine review for the scientific record. sign in

Revisiting multi- modal positional encoding in vision–language models

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

ZAYA1-VL-8B Technical Report

cs.CV · 2026-05-08 · unverdicted · novelty 4.0

ZAYA1-VL-8B is a new MoE vision-language model with vision-specific LoRA adapters and bidirectional image attention that reports competitive performance against several 3B-4B models on image, reasoning, and counting benchmarks.

citing papers explorer

Showing 1 of 1 citing paper.

  • ZAYA1-VL-8B Technical Report cs.CV · 2026-05-08 · unverdicted · none · ref 79

    ZAYA1-VL-8B is a new MoE vision-language model with vision-specific LoRA adapters and bidirectional image attention that reports competitive performance against several 3B-4B models on image, reasoning, and counting benchmarks.